{"id":"W4411374363","doi":"10.1145/3722212.3725097","title":"Demonstrating CatDB: LLM-based Generation of Data-centric ML Pipelines","year":2025,"lang":"en","type":"article","venue":"","topic":"Advanced Data Storage Technologies","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Pipeline transport; Engineering; Mechanical engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001884208,0.00009094866,0.0001236371,0.0001853943,0.0000716064,0.00005052816,0.001670851,0.00005216842,0.000005140256],"category_scores_gemma":[0.0003370417,0.00007915505,0.00001646307,0.000815113,0.00005924435,0.0008670642,0.0006923967,0.00007572322,0.000005939768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002490584,"about_ca_system_score_gemma":0.0001424779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003499669,"about_ca_topic_score_gemma":0.00005790888,"domain_scores_codex":[0.9990388,0.00002316115,0.0002664136,0.000382398,0.0001414872,0.0001477],"domain_scores_gemma":[0.9981735,0.0001084134,0.0000986655,0.001516261,0.00008736479,0.00001574557],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002976993,0.0001565179,0.001431906,0.000050749,0.00001666596,0.000009392814,0.00002039988,0.003458067,0.03328485,0.238427,0.01559876,0.7075428],"study_design_scores_gemma":[0.0002001003,0.00002184228,0.0001026261,0.00001567508,0.000005986795,0.000001174899,0.00002486581,0.8813522,0.1143293,0.001928494,0.001917323,0.0001004392],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003000965,0.0002533514,0.9942184,0.0009936283,0.0001595191,0.0001094206,0.00001781623,0.0004597452,0.0007871161],"genre_scores_gemma":[0.3966159,0.000008783666,0.6030495,0.0001739416,0.00001500222,0.000003968627,0.00004826509,0.000002167921,0.00008242132],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8778942,"threshold_uncertainty_score":0.3227849,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07181776484659808,"score_gpt":0.3211208289744126,"score_spread":0.2493030641278146,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}